© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108447
    Prev
    Next
    INDEX
    Explanations

    Technical and code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ天
    -0.50
    ä¸Ģ个
    -0.50
    ä¸Ģè¾Ĩ
    -0.47
     unit
    -0.45
    ä¸Ģæŀļ
    -0.45
     اÙĦÙĪاØŃد
    -0.44
     single
    -0.44
    ä¸Ģæľµ
    -0.44
    åįĬ个
    -0.43
    ä¸Ģåı°
    -0.42
    POSITIVE LOGITS
    ispers
    0.28
    ầm
    0.28
    agrams
    0.26
    batis
    0.25
    AxisAlignment
    0.24
    ายà¸Ļ
    0.23
    å·²ä¹ħçļĦ
    0.23
     key
    0.23
     multiline
    0.23
    TOR
    0.23
    Activations Density 0.950%

    No Known Activations